A new approach for mediation analysis: Is Baron and Kenny's method still valid?

Baron and Kenny’s (1986) causal steps approach has been widely used by scholars in mediation analyses. Yet, recently, some scholars have begun to argue that Baron and Kenny’s approach is not an appropriate method for mediation analysis (Fritz and MacKinnon, 2007; Gürbüz, 2021; Hayes, 2018). Instead, the use of contemporary methods based on
bootstrapping would yield more valid and reliable results in the analysis of mediation models (Fritz and MacKinnon, 2007; Gürbüz, 2021; Hayes, 2018; Hayes and Rockwood, 2017; Preacher and Selig, 2012; Williams and MacKinnon, 2008). Methodical studies on the differences between these two approaches are scarce. The aim of the present study is to (1) discuss the basic assumptions of both the causal steps approach and the contemporary approach in mediation analysis (2) to show the differences between the results of the two competing approaches by using real data set.